“…The selected models include PSNR, SSIM, MS-SSIM [62], FSIM [63], BRISQUE [64], and BMPRI [65], DB-CNN [34], and DipIQ [66], representing 2D-IQA models. S-PSNR [6], WS-PSNR [6], SSP-BOIQA [11], Yun et al [12], MC360IQA [20], Zhou et al [23], VGCN [25], AHGCN [35], and S 3 DAVS [16], representing 360-IQA models. MC360IQA, Zhou et al, VGCN, and AHGCN are all deep learning-based solutions using the multichannel paradigm with a varying number of channels, from six to twenty, making them highly complex models.…”